Are VS Code or browser extensions available?

Yes — a Visual Studio Marketplace extension embeds the UI, but Automation Skill Builder must still run locally. A Microsoft Office add-in remains under evaluation.

INTELLIGENCE, BEYOND HERE & NOW

AI that is not limited to here and now.

Bring distant intelligence onto the site.
Leave today’s results for later.
ASB closes the AI capability gap across environments.

Try it yourself ↗ Meet ASB →

Works with the AI tools you already use CursorClaudeGitHub CopilotClineMCP

Two ways to arrive

Across space

Intelligence and execution,
each where they are needed.

AI understands the task on one side; ASB acts in the target environment. Network remote and optical air-gap give different ways to arrive.

Independent live execution →

Across time

One success becomes
repeatable capability.

Record, refactor, and parameterize what already works. Leave an automation asset you can deploy next time.

Capture and reuse →

TRY ASB

Start from one real task.

Use demo mode or bring your own key. Connect a running ASB to execute, record, and generate skills.

Open the live trial ↗

Try ASB now — no setup neededLocal MCP

Demo mode Bring your own key

“Open a page, extract product names and prices, save as CSV.”

Local connect · scan QR · tools · chat

Try ASB now — no setup needed

Local MCP

Guided demo — no API key needed

Demo scenario

Scenario fixed for demo — custom prompts in bring-your-own-key mode

1

Install ASB and start the local service

Download the installer and run it. The desktop app listens on 127.0.0.1:8800 by default.
2

Turn on Recording in ASB

In the desktop app, click New skill → Start recording.
3

Run the demo scenario

ASB runs the preset workflow. Watch the log for progress.

Demo running — do not close this panel. ASB is controlling your browser.

4

Stop recording in ASB

When the log shows completion, click Stop recording in the desktop app.
5

Generate the executable skill

In ASB, click Generate skill to compile the recording into a reusable automation.

Automation Skill Builder base URL

LLM provider (OpenAI-compatible)

Model id

API key

Service API key (optional)

Max tool rounds

Max tool output chars

Request timeout(s)

Phone remote: in the desktop app open Settings → Phone remote, start Cloudflare tunnel, then scan the QR here (or import a saved QR image). Connection and AI settings apply automatically — no need to re-enter them here.

BUILT FOR REAL WORK

Capability lands in actual work.

See more →

WEB / DATA

Web pages become data.

Describe a capture task in natural language. Browser tools read the page and write structured output.

Try the web demo →

DESKTOP / REUSE

Desktop steps become capability.

Record what already works, extract changing inputs, and hand the repeatable flow to a reusable program.

Reuse across time →

ERP / BUSINESS

Business systems, wired to AI.

Use configured SAP (or similar) connections to run concrete operations in the environment you already have.

Talk about your scenario ↗

ONE EXECUTION FOUNDATION

One execution base,
two ways to deliver.

Desktop, browser, files, vision, and APIs connect inside ASB. After a live action, recording and packaging are optional — your task decides.

Download and integrations →

Choose how you will use ASB — ASB workspaceProduct screenshots

Workspace cards after you pick a path — ASB workspaceProduct screenshots

PROMPT EXAMPLES

Tell the AI what to do — in plain language

Paste a prompt into your MCP client. ASB executes locally — browser, desktop, ERP — and reports each step back.

amazon.com

Open amazon.com, search "iPhone 17", extract product names and prices from the results page, and save them as iphone_prices.csv on the desktop.

EXECUTING

Opened amazon.com
Searched "iPhone 17"
Extracted 12 product rows
Wrote iphone_prices.csv to Desktop

WEB · DATA

Amazon price capture

Browser automation from a single sentence — no selectors to hand-code.

Try this example →

MCP · ASB · AI design

Use MCP ASB to enable AI design mode, record desktop steps via MCP tools (not WinMCP), save as pass_action.py, run AI parameter analysis, and package as exe.

EXECUTING

mcp: enable AI design · start_recording
wait 2s → click (1406, 257)
Ctrl+A → clipboard DGJW26010091 → paste
click (492,373) → (410,933) → (635,270) …
stop_recording → pass_action.py
mcp: ai_analyze_params (code, tip)
mcp: package_exe

AI DESIGN

Record, parameterize, package

Let the assistant drive ASB MCP tools — record desktop steps, analyze parameters, ship an exe.

Download ASB →

164_sap_sap · SAP GUI

Use MCP ASB tools starting with 164_sap_sap — prefer an existing connection (create one only if none exists). Open transaction ZVF04 to maintain the invoice due-date list, wait 5s, then enter sales organization 1010.

EXECUTING

164_sap_sap_list_connections
164_sap_sap_open · existing connection
Transaction ZVF04 — invoice due list
wait 5s
input sales org 1010

ERP

SAP invoice due list

Reuse configured SAP connections — the assistant navigates GUI transactions via MCP.

ERP design partner →

Version 0.9.0 · Windows installer (.exe), macOS disk image (.dmg), or ZIP archives

Other downloads (ZIP)

One more thing — extensions

If you want to work more deeply with your existing AI tools and desktop workflows, we offer optional extensions for flexible access. The Automation Skill Builder application must still be running locally (often in the background); extensions only embed the web UI—point them at the same URL you use in a browser.

VS Code–compatible editors

Install from the Visual Studio Marketplace (recommended) or a downloaded .vsix in editors that support the VS Code extension format, including Visual Studio Code, Cursor, Google Antigravity, and similar hosts.

Visual Studio Marketplace Download VSIX (0.1.2)

From the Marketplace: Open the listing, click Install, then in settings search for Automation Skill Builder and set automationSkillBuilder.baseUrl to your running service (for example http://127.0.0.1:8800/).
From a VSIX: Open Extensions → ⋯ → Install from VSIX…, choose the file, then set automationSkillBuilder.baseUrl the same way.

Chrome & Edge (side panel)

The same side-panel package works in Google Chrome and Microsoft Edge (Chromium). Download the ZIP, extract it, then load the folder as an unpacked extension.

Download Chrome extension (ZIP)

Unzip so the folder contains manifest.json. Open chrome://extensions or edge://extensions, turn on Developer mode, click Load unpacked, and select that folder. In the side panel, set host/port to match your running app (defaults align with 127.0.0.1:8800).

Reminder: Extensions do not start the backend. Keep Automation Skill Builder running on your machine and use the same address and port in the extension as in your browser so the embedded UI can load.

SUBSCRIPTION LICENSE

Simple, honest pricing

Each time an AI assistant invokes a skill via MCP, that counts as 1 call. A typical automation run uses around 20–30 calls.

Start free — no credit card needed. Every account gets 1,000 calls per month at no cost, resetting on the 1st of each month (your local time). When you're ready to do more, upgrade any time.

FREE

1,000 calls / month

≈ 33–50 skill runs / month

Get started

STARTER

$9 / mo

5,000 calls / month

≈ 165–250 skill runs / month

Questions & answers

Short answers for common pre-sales and install questions.

What are the system requirements?

Summarized for operators and procurement. Pre-built desktop bundles target Windows and macOS (executable + supporting files).

Baseline (bundled app): The ZIP includes what you need to start the service—no separate Python install is required as a precondition. Use a 64-bit OS, reserve 8 GB+ RAM for heavier OCR / ML / desktop workloads, allow several GB of disk for caches on first runs, and use a current browser for the local web UI (often http://127.0.0.1:8800). Optional Python or Node.js may be needed for specific skills.

Windows

64-bit Windows 10 or later (or supported Server). Extract the ZIP and launch the packaged executable; allow prompts for permissions as documented.

WSL counts as Linux for dependencies, not Windows-native UI automation. Optional runtimes (Python, Node.js) may be required for specific skills.

macOS

Use a recent macOS release that runs the distributed bundle. Extract the ZIP and open the app; approve Accessibility / Input Monitoring when the system prompts.

Optional runtimes (Python, Node.js) may be required for specific skills; browser automation also needs MCP configuration in the app.

Linux

The Linux edition suits Debian-based environments. Because deliverables can be large, please reach out to us (or your maintainer) for details on distribution and how to obtain the build.

Headless or server deployments may require DISPLAY or --no-gui.

Is this a hosted SaaS?

No. It is designed primarily as a self-hosted application you run on your infrastructure or workstation. You control networking, TLS, and who can reach the service.

Do I need MCP or Claude community skills?

No. Core features work over the web UI and HTTP API. MCP and integration with the rich skill ecosystem on the Claude community are optional when you want assistants or a skill runtime to consume packaged capabilities. We fully support that path: use the in-app skill manager to install the skills you prefer, use the product’s built-in security checks to validate them, and execute with confidence.

Will this replace my team?

No — it amplifies what your team can do. Think of it as a capable assistant that drafts and suggests; your team reviews, decides, and owns the outcome.

What about data privacy?

Sensitive data flows depend on your configuration: local execution, which models you call, and which external services you enable. Run data-protection assessments before processing regulated data. With this product’s design, interactions are auditable and can be reviewed in a visual way—helping security teams verify behavior instead of working blind.

Why local-first?

Many automation tasks touch the desktop, filesystem, or internal APIs. Keeping execution close to the environment reduces latency and can simplify compliance—at the cost of you maintaining the runtime.

Does execution call the cloud?

At runtime, zero cloud or AI calls for skill execution — invocation, quota, and license checks stay on your machine. AI is used when you record / author (with the model you configure), not on every rerun.

Paid tiers still need a periodic license.json refresh (~every 30 days) from our site. That is a one-time file update, not a per-run network dependency.

What happens if I stay offline past my license expiry?

If your license is still valid (expires_at hasn't passed), you can run completely offline indefinitely until it expires.
If expires_at passes while offline, the app automatically falls back to the Free tier (1,000 calls/month) until you reconnect and refresh your license.
If you cancel your subscription but your license file hasn't expired yet, you'll continue running at your paid tier locally until expiry — this is a known trade-off of the offline-first design.

Note: like most offline license systems, this relies on your system clock being roughly accurate. We don't currently implement clock-tamper detection — this is a deliberate trade-off in favor of true offline operation.

Will VS Code, Chrome, or Office integrations be available?

Yes—see the Visual Studio Marketplace listing or download a VSIX. The Automation Skill Builder app must still run locally; extensions only embed the UI. A Microsoft Office add-in remains under evaluation.

What if OCR or vision is slow the first time?

Vision stacks often download models on first use. Expect a longer cold start; subsequent runs are typically faster. Warmup and skip flags are available in the app settings.

How do I get help?

Community users can ask questions in the public forum — response times vary. If your team needs reliable support with a guaranteed response, check out our professional plan.

Do I need Python or Node.js installed?

No. The bundled app includes what you need to start the service—no separate Python install is required as a precondition. Optional Python or Node.js may be needed for specific skills. Pre-built bundles target 64-bit Windows 10+ and recent macOS.

Support model

Two lanes—so expectations stay clear whether you are evaluating, self-hosting, or running under a commercial agreement.

Community & as-is use

The software may be used and inspected according to its license and repository terms. Documentation, issues, and community discussion (where offered) are provided without warranty.

Community support is best-effort — driven by fellow users and the maintainer when possible. It’s ideal for exploring, learning, and running personal or internal projects. For teams that need faster answers or hands-on help, professional support is available separately.

Professional support

For organizations that need onboarding, priority help, custom integrations, security review assistance, or deployment hardening, commercial support may be available from the maintainer or partners.

Scope, channels, and SLAs are defined in a separate agreement—not on this marketing page. Contact your vendor or project owner for entitlement and pricing.

Contact

Billing and subscriptions: info@visualbuild.me

Technical and product issues: dev@visualbuild.me

AI that is not limited to here and now.

Intelligence and execution,
each where they are needed.

One success becomes
repeatable capability.

Start from one real task.